Salesforce MCP Server (SameerShrivastava-SF/Salesforce-MCP) is an MCP server listed on the M8ven Trust Index. It scores 46 out of 100, grade D. It declares 59 tools. No publisher has claimed this listing.

D
Caution
46/100

Salesforce MCP Server

A comprehensive server that transforms Claude Desktop into a Salesforce IDE for managing metadata, executing SOQL queries, and automating multi-org operations. It provides 60 optimized tools for intelligent debugging, bulk data management, and Apex testing through natural language commands.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

SameerShrivastava-SF

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — analyze_field_usage (line 925: with open(csv_file_path, 'w', newline='', encoding='utf-8') as csvfile:)
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes59 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

compare_profiles

Compare two Salesforce profiles and show their differences.

compare_permission_sets

Compare two permission sets and show their differences.

compare_object_field_counts

Compare field counts and field details for an object between same or different orgs.

find_similar_fields_across_objects

Find similar or matching fields between two different objects.

compare_org_object_counts

Compare total object counts and types between two orgs.

list_batch_jobs

List Batch Apex jobs.

get_batch_job_details

Get detailed information about a batch job.

list_scheduled_jobs

List scheduled Apex jobs.

abort_batch_job

Abort a running batch job.

delete_scheduled_job

Delete a scheduled job.

execute_anonymous_apex

Execute anonymous Apex code.

get_debug_logs

Retrieve recent debug logs.

get_debug_log_body

Get the full body of a debug log.

get_bulk_job_status

Get status of a bulk API job.

deploy_metadata

Deploy Salesforce metadata (create or update). Supports 16 metadata types.

fetch_metadata

Fetch Salesforce metadata by type and name. Supports 16 metadata types.

list_metadata

List metadata of a specific type with optional filtering.

bulk_operation

Perform bulk operations on Salesforce records using Bulk API 2.0.

export_data

Export Salesforce data in various formats.

soql_query

Execute SOQL query or build and execute using parameters.

get_object_metadata

Get comprehensive object metadata including fields and relationships.

manage_user_permissions

Manage user permissions, profiles, and permission sets.

get_record_count

Get count of records in an object.

export_schema_to_json

Export object schema(s) to JSON.

diagnose_and_fix_issue

Diagnose and optionally fix Salesforce issues including triggers, flows, validation rules, layouts, fields, permissions, formulas, and more.

get_metadata_deploy_status

Return the status and (optional) component failures/successes for a metadata deploy job.

fetch_object_metadata

Return describe() + record type info for any object.

execute_soql_query
list_connected_orgs

List all connected Salesforce orgs.

switch_active_org

Switch to a different connected org.

compare_metadata_between_orgs

Compare metadata between two connected orgs.

compare_object_schemas

Compare object schemas between two orgs.

get_org_differences_summary

Get a high-level summary of differences between two orgs.

salesforce_production_login

Login to Salesforce production org.

salesforce_sandbox_login

Login to Salesforce sandbox org.

salesforce_custom_login

Login to custom Salesforce domain.

salesforce_logout

Clear stored tokens.

salesforce_auth_status

Check authentication status.

salesforce_get_domain_from_url

Extract the domain parameter from a Salesforce org URL for use with login.

salesforce_login_username_password

Login to Salesforce using username and password.

salesforce_health_check

Comprehensive health check for Salesforce connection and org status.

get_org_limits

Get Salesforce org limits (API calls, storage, etc.).

get_org_info

Get Salesforce org information.

get_current_user_info

Get current user information.

list_installed_packages

List all installed managed packages in the org.

get_api_usage_stats

Get API usage statistics for recent days.

query_with_related_records

Query parent records with related child records.

analyze_object_dependencies

Analyze dependencies for an object.

find_unused_fields

Find potentially unused fields on an object.

generate_object_diagram

Generate entity relationship diagram data for objects.

list_all_objects

List all objects in the org.

get_field_usage_stats

Get statistics about field usage (null values, etc.).

test_field_analysis

Quick test version of field analysis - analyzes ONE field only (for testing).

analyze_field_usage

Comprehensive field usage analysis - find where fields are used across all metadata.

run_apex_tests

Run Apex tests and return results with code coverage.

get_apex_test_coverage

Get code coverage for Apex classes.

list_apex_test_classes

List all Apex test classes in the org.

list_available_profiles

List all available profiles in the org.

list_available_permission_sets

List all available permission sets in the org (excluding profile-based ones).

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configSFMCP_HTTP_HOST
configSFMCP_HTTP_PORT
configRENDER
configSFMCP_OAUTH_DISABLED
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

59/59 tools missing one or more hints — compare_profiles (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compare_permission_sets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compare_object_field_counts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +56 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — analyze_field_usage (line 925: with open(csv_file_path, 'w', newline='', encoding='utf-8') as csvfile:)

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

47/59 tool handlers declare input schemas (80%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

56/59 tool handlers wrap calls in try/catch (95%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Tool description accuracy

analyze_field_usage: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sameershrivastava-sf/salesforce-mcp?variant=verified)](https://m8ven.ai/mcp/sameershrivastava-sf/salesforce-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: fac0b6ce37ac1d91124116d0cce25fb7ade7284e
code hash: c3174b9ca4050df8dec938f2350e258d1af4492a7f21b34bf4385189dbd9537e
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client